Skip to content
Preprint

Concept Drift Detection and Adaptive Retraining of Malware Classification Models

Aug 2026 · 0 citations · 62 references
Computer Science

TL;DR

This chapter analyzes two machine learning-based approaches to automated concept drift detection-a novel approach based on One-Class Support Vector Machines (OCSVM) and a previously-studied technique based on Minibatch K-Means (MK-Means), which achieve classification accuracy comparable to periodic retraining, while offering substantially greater efficiency in terms of the number of models that must be retrained.

Abstract

Concept drift refers to changes over time in the statistical properties of data, as compared to the data that was used to train a learning model. Machine learning models for malware detection or classification are particularly susceptible to performance degradation caused by concept drift, as attackers constantly modify existing malware. In this chapter, we analyze two machine learning-based approaches to automated concept drift detection-a novel approach based on One-Class Support Vector Machines (OCSVM) and a previously-studied technique based on Minibatch K-Means (MK-Means). For comparison we also consider Maximum Mean Discrepancy (MMD), a statistical technique for detecting changes in multidimensional data. We conduct an extensive series of experiments comparing the effectiveness of four learning models, namely, Multilayer Perceptron, Random Forest, Support Vector Machines, and eXtreme Gradient Boosting. For each of these models, we consider three distinct scenarios: A static scenario where no model retraining occurs, a periodic scenario where models are constantly retrained irrespective of concept drift, and a drift-aware scenario where models are only retrained when concept drift is detected. Under the drift-aware scenario, we analyze the tradeoff between accuracy and training efficiency using Pareto Front analysis. We find that all three concept drift detection techniques achieve classification accuracy comparable to periodic retraining, while offering substantially greater efficiency in terms of the number of models that must be retrained. In addition, drift-aware retraining based on our OCSVM technique generally outperforms the MK-Means and MMD approaches. Overall, these results provide strong evidence that we can accurately detect concept drift in malware classification models.

View source

Similar papers

Open access Aug 2026

Empirical Evaluation and New Insights of Concept Drift in ML-Based Android Malware Detection

Despite outstanding results, machine learning-based Android malware detection models struggle with concept drift, where rapidly evolving malware characteristics degrade model effectiveness. This study examines the impact of concept drift on Android malware detection, evaluating two datasets and nine machine learning an...

Ahmed Sabbah, Mohammed F. Kharma, Radi Jarrar et al. · 1 citation
Open access Aug 2026

Adaptive malware detection under concept drift: an evolutionary deep learning framework with GA-based retraining

The proposed adaptive framework mitigated this performance degradation by incorporating GA-generated feature patterns during retraining, improving the accuracy to 97.7% on the same dataset, indicating the effect of concept drift.

Zahraa Salim Dawood, Amel H. Abbas · 0 citations
Conference Aug 2026

Hybrid Representation Learning for Robust Multiclass Malware Classification Under Class Imbalance

The increasing sophistication of modern malware, particularly in the form of polymorphic and packed variants, poses significant challenges to traditional detection systems. While machine learning-based approaches have shown promise, many existing methods rely on single feature representations and are evaluated using me...

Akshaya Mogili, G. Lishita, R. N · 0 citations
Open access Aug 2026

From Drift Detection to Diagnosis: An Explainable Framework for Deployed Machine Learning

A unified drift-aware framework for explainable diagnostics in deployed machine learning systems is proposed that can support proactive model monitoring and assist practitioners in deciding whether continued monitoring, investigation, recalibration, or model retraining is required.

Tambe Ankit Sampat · 0 citations
Aug 2026

iLEAD: an efficient incremental learning with evolutionary approach for classification

The proposed iLEAD method combines hybrid genetic programming with a CART classifier, offering improved predictive performance, reduced processing time, and lower memory usage compared to traditional GP-based decision trees, making it ideal for incremental learning in dynamic datasets.

Ibadonbok Syiemlieh, Sufal Das · 0 citations
Review Open access Aug 2026

A Comparative Evaluation of Malware Families and Machine-Learning Detection Techniques, and an Optimized Stacked-Ensemble Model for Predicting Software Maliciousness

An efficient stacked-ensemble model that estimates how likely a given executable is to be malicious and is compared against recent malware research/types are compared and identified for future research work/area.

Deepak Singh Rana, S. Dimri · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.